US4783804A - Hidden Markov model speech recognition arrangement - Google Patents

Hidden Markov model speech recognition arrangement Download PDF

Info

Publication number
US4783804A
US4783804A US06714517 US71451785A US4783804A US 4783804 A US4783804 A US 4783804A US 06714517 US06714517 US 06714517 US 71451785 A US71451785 A US 71451785A US 4783804 A US4783804 A US 4783804A
Authority
US
Grant status
Grant
Patent type
Prior art keywords
signals
signal
markov model
state
speech
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Expired - Lifetime
Application number
US06714517
Inventor
Biing-Hwang Juang
Stephen E. Levinson
Lawrence R. Rabiner
Man M. Sondhi
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Nokia Bell Labs
Original Assignee
Nokia Bell Labs
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Grant date

Links

Images

Classifications

    • GPHYSICS
    • G10MUSICAL INSTRUMENTS; ACOUSTICS
    • G10LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00Speech recognition
    • G10L15/08Speech classification or search
    • G10L15/14Speech classification or search using statistical models, e.g. Hidden Markov Models [HMMs]

Abstract

Markov model speech pattern templates are formed for speech analysis systems by analyzing identified speech patterns to generate frame sequences of acoustic feature signals representative thereof. The speech pattern template is produced by iteratively generating succeeding Markov model signal sets starting with an initial Markov model signal set. Each iteration includes forming a set of signals representative of the current iteration Markov model of the identified speech pattern responsive to said frame sequences of acoustic feature signals and one of the previous Markov model signal sets and comparing the current iteration Markov model signal set with said previous Markov model signal set to generate a signal corresponding to the similarity therebetween. The iterations are terminated when said similarity signal is equal to or smaller than a predetermined value and the last formed Markov model signal set is selected as a reference template for said identified speech pattern. The state transition model has increased accuracy by grouping the feature signals into related clusters corresponding to states of the previous state transitional model, whereby with further grouping of the feature signals the continuous probability density function acquires components representing a mixture of different continuous probability density functions.

Description

Our invention relates to pattern recognition and, more particularly, to arrangements for analyzing patterns using Markov modeling.

BACKGROUND OF THE INVENTION

In communication, data processing and other information systems, it is desirable to provide speech recognition input and synthesized voice output for inquiries, commands, and exchange of information. Such speech interface facilities permit interaction with data processing equipment from remote locations without expensive terminal equipment and allows a user to communicate with computer type devices in a natural manner without manually operated keyboards. While the advantages of speech interface facilities are well known, providing the speech recognition accuracy required for commercial use has presented formidable technical problems. Accurate speech recognition is relatively difficult to achieve because of the complexity of speech patterns and variations thereof among speakers. Acceptable results have been obtained in specialized applications where the recognition is restricted to particular individuals using constrained vocabularies. The success of automatic speech recognition equipment, however, is very limited where there is no restriction on the number of speakers or where the vocabulary of speech patterns to be identified is large.

Speech recognition arrangements generally are adapted to convert an unknown speech pattern to a sequence of prescribed acoustic features which is then compared to stored sets of acoustic feature sequences representative of previously identified speech patterns. As a result of the comparison, the unknown speech pattern may be identified as the stored set having the most similar acoustic feature sequence on the basis of predetermined recognition criteria. Recognition accuracy of such systems is highly dependent on the acoustic features that are prescribed and the recognition criteria used.

The comparison between an unknown speech pattern and the stored reference sets may be direct or may be adjusted to take into account differences in speaking rate and differences in articulation. Some speech recognition systems employ dynamic programming to determine the optimum alignment between patterns. Such dynamic time warping mitigates the effects of variations in speech rate and articulation on recognition accuracy. The signal processing arrangements for dynamic time warp comparisons, however, are complex and the time needed for recognition of a speech pattern is a function of the size of the reference pattern vocabulary as well as the speed of operation of the recognition equipment. Where the recognition is speaker independent, the number of reference patterns is very large so that real time recognition of a pattern for vocabularies of the order of 50 words is difficult to achieve with acceptable accuracy.

Another approach to automatic speech recognition uses probabilistic modeling, e.g., Markov models, in which the sequence of acoustic features of a speech pattern is patterned into a series of transitions through a set of states based on statistical estimates. Speaker dependent recognition arrangements such as described in the article, "The DRAGON System-An Overview", by James K. Baker, appearing in the IEEE Transactions on Acoustics, Speech and Signal Processing, Vol. ASSP-23, No. 1, February 1975, pp. 24-29, have been devised in which acoustic spectral feature sequences corresponding to speech patterns are generated and evaluated in a series f hierarchical Markov models of acoustic features, words and language. The acoustic feature sequences are analyzed in Markov models of phonemic elements. The models are concatenated into larger acoustic elements such as words and the results are then processed in a hierarchy of Markov models, e.g., syntactic, contextual, to obtain a speech pattern identification. The use of concatenated phonemic element models and the complexity involved in unrestricted hierarchical Markov modeling, however, requires many hours of system training by each identified speaker to obtain a sufficient number of model tokens to render the Markov models valid.

A speaker indeendent recognition system described in the article, "On the Application of Vector Quantization and Hidden Markov Models to Speaker-Independent, Isolated Word Recognition", by L. R. Rabiner, S. E. Levinson, and M. M. Sondhi, appearing in The Bell System Technical Journal, Vol. 62, No. 4, April 1983, pp. 1075-1105, employs a relatively simple Markov model having a restricted number of states and state transitions. Advantageously, this speaker independent arrangement reduces the complexity of recognition processing so that the speed of identification of a speech pattern is less dependent on vocabulary size and the capabilities of the processing devices. As a result, real time recognition is obtained.

While speech recognition processing may be simplified using Markov modeling, the generation of the signals that form the models of reference patterns to which an unknown pattern is compared is complex and time consuming and subject to inaccuracies. These factors have inhibited the practical application of Markov model speech recognition. It is an object of the invention to provide improved automatic speech recognition based on Markov modeling that includes faster and more accurate model formation.

BRIEF SUMMARY OF THE INVENTION

The objects of the invention are achieved by forming a succession of Markov models that have continuous probability density functions with mixture components and that are convergent from a stored data base of speech pattern feature signal sequences, comparing the successive models until a prescribed similarity between successive models is achieved, and reestimating the last successive model so that a highly accurate Markov model template of the speech pattern is obtained.

The invention is directed to a speech analysis arrangement in which speech pattern reference templates are formed for speech recognition. In the training procedure, identified speech patterns are analyzed to generate successive sets of signals having continuous probability density functions, rather than having discrete representations. Each set is representative of a Markov model of the identified pattern. The speech pattern template is produced by iteratively generating succeeding Markov model signal sets starting with an initially selected Markov model signal set. Each iteration includes forming a set of signals having continuous density functions with mixture components representative of the current iteration Markov model of the identified speech pattern responsive to said frame sequences of acoustic feature signals and one of the previous Markov model signal sets and comparing the current iteration Markov model signal set with the previous Markov model signal set to generate a signal corresponding to the similarity therebetween. The iterations are terminated when the similarity signal is equal to or less than a predetermined value. The resulting template is then used as a reference pattern for unknown speech patterns being analyzed, according to known maximum likelihood techniques, but using patterns to be tested which are derived in an analogous fashion to that of the templates.

BRIEF DESCRIPTION OF THE DRAWING

FIG. 1 shows a schematic diagram of a constrained hidden Markov model of a pattern such as used in the invention;

FIG. 2 shows waveforms illustrating the likelihood of features and discrete and continuous approximations thereto for a Markov model;

FIG. 3 depicts a general flow chart of the method of generating a Markov model illustrative of the invention;

FIGS. 4-6 depict a detailed flow chart of the Markov model generating method of FIG. 3;

FIG. 7 shows a block diagram of a Markov model generating circuit illustrative of the invention;

FIG. 8 illustrates the acoustic feature sequence storage arrangement in the circuit of FIG. 7;

FIG. 9 shows a detailed flow chart illustrating Markov model speech pattern time frame alignment operations in FIG. 4;

FIG. 10 shows the arrangement of signals in the state-frame store of the circuit of FIG. 7;

FIG. 11 is a flow chart detailing the observation symbol sequence formation of FIG. 6;

FIG. 12 is a flow chart detailing the Markov model reestimation step of FIG. 6;

FIG. 13 depicts a block diagram of a speech recognition circuit utilizing the Markov model reference templates of the invention; and

FIG. 14 is a flow chart illustrating the operation of the recognizer of FIG. 13.

GENERAL DESCRIPTION

As is well known in the art, a hidden Markov model may be used to evaluate the probability of occurrence of a sequence of observations O1,O2, . . . Ot, . . . ,OT, where each observation Ot may be either a discrete symbol or a continuous vector. The sequence of observations may be modeled as a probabilistic function of an underlying Markov chain having state transitions that are not directly observable. FIG. 1 illustrates such a model. Referring to FIG. 1, there are N, e.g., 5 states. The transitions between states are represented by a transition matrix A=[aij ]. Each aij term of the transition matrix is the probability of making a transition to state j given that the model is in state i. The output symbol probability of the model is represented by a set of functions B=[bj (Ot)], where the bj (Ot) term of the output symbol matrix is the probability of outputting observation Ot, given that the model is in state j. The model of FIG. 1 is constrained so that state 1 is always the initial state for the first time frame of the utterance, only a prescribed set of left-to-right state transitions are possible, and a predetermined final state is defined from which transitions to other states cannot occur. These restrictions are shown in the model state diagram of FIG. 1 in which state 1 is the initial state, state 5 is the final or absorbing state, and the prescribed left-to-right transitions are indicated by the directional lines connecting the states.

From state 1 in FIG. 1, it is only possible to reenter state 1 via path 111, to proceed to state 2 via path 112, or to proceed to state 3 via path 113. Transitions are restricted to reentry of a state or entry to one of the next two states. Such transitions are defined in the model as transition probabilities. For example, a speech pattern currently having a frame of feature signals in state 2 has a probability of reentering state 2 of a22, a probability a23 of entering state 3 and a probability of a24 =1-a21 -a22 of entering state 4. The probability a21 of entering state 1 or the probability a25 of entering state 5 is zero and the sum of the probabilities a21 through a25 is one.

In each state of the model, the current feature frame may be identified with one of a set of predefined output symbols or may be labeled probabilistically. In this case, the output symbol probability bj (Ot) corresponds to the probability assigned by the model that the feature frame symbol is Ot. The model arrangement then comprises a matrix A=[aij ] of transition probabilities and a technique of computing B=bj (Ot), the feature frame symbol probability in state j.

According to the invention, a Markov model is formed for a reference pattern from a plurality of sequences of identified training patterns and the output symbol probabilities are multivariate Gaussian function probability densities. The constrained hidden Markov model is used to derive a set of reference pattern templates, each template representative of an identified pattern in a vocabulary set of reference patterns. The Markov model reference templates are then utilized to classify a sequence of observations as one of the reference patterns based on the probability of generating the observations from each Markov model reference pattern template. The unknown pattern can then be identified as the reference pattern with the highest probability.

For speech recognition, an unknown input speech pattern is analyzed to generate a time frame sequence of acoustic features. Each feature may be a spectral feature, a linear prediction coefficient vector or other acoustic features well known in the art. The generated feature sequence for the unknown speech pattern, e.g., a word or phrase, forms the observation sequence O and the probability that O has been generated by a Markov model reference template λ of a word or phrase of a vocabulary set is determined in accordance with ##EQU1## where i1,i2, . . . ,iT is the sequence of Markov model states and O1,O2, . . . ,OT is the observed sequence of speech pattern frame features. Equation (1) may be written in terms of the forward partial probability αt (i) defined as

α.sub.t (i)=L(O.sub.1,O.sub.2, . . . O.sub.t and state i at time t|λ)                                      (2)

αt+1 (j) can then be evaluated as ##EQU2## so that equation (1) becomes ##EQU3## After the probability signal for each Markov model reference pattern has been generated, the input speech pattern may be identified as the reference pattern model r corresponding to the highest likelihood signal L(O|λr) (r=1,2, . . . ,R), where R is the number of words in the vocabulary.

The recognition scheme disclosed in U.S. patent application Ser. No. 434,516, filed Sept. 2, 1982, discloses an arrangement that utilizes vector quantization to generate Markov model output symbol probability signals b(Ot). While vector quantization techniques permit the use of permanently stored probability tables, the resulting model probabilities are only an approximation to the actual likelihood. The graph of FIG. 2 illustrates the effect of the vector quantized approximation.

In FIG. 2, curve 201 represents the actual likelihood b(Ot) as a function of acoustic features, and the vertical lines correspond to the discrete probability values of the discrete vector quantized features. An input acoustic feature derived from a speech pattern is first quantized to the nearest prototype feature and the probability of the prototype feature is selected as b(Ot). It is readily apparent that an input feature at x1 on the feature axis corresponds to a probability y1 from curve 201 but that the probability for the nearest prototype vector 205 is y2. The difference between y1 and y2 is the error due to quantization and the error affects the accuracy of speech pattern recognition.

It is therefore desirable to reduce the deviation from the actual probability density function 201 by using a multivariate Gaussian function approximation of the form ##EQU4## where N (x, μ, σ) denotes a D-dimensional normal density function of mean vector μ and covariance matrix σ, M is the number of mixtures, and C is the mixture gain matrix. Such a multivariate Gaussian function is illustrated as curve 210 in FIG. 2. The multivariate Gaussian function of equation 5 is a linear combination of M Gaussian functions adjusted according to mixture coefficients C so that the probability density of the Markov model can be approximated to any degree of accuracy. The combination is analogous to the approximation of a function using sine and/or cosine waves in Fourier analysis. In accordance with the invention, the difference between the likelihood signal b(Ot) obtained from curve 210 (derived from equation (5)) and the actual probability density curve 201 is small so that the accuracy of speech pattern recognition from Markov model templates using b(Ot) is substantially improved.

The flow chart of FIG. 3 illustrates the general method of forming a Markov model template from a training set of speech patterns. Initially, a large number of speech patterns is analyzed to generate frame sequences of acoustic features. Assume for purposes of illustration that the speech patterns correspond to utterances of the digits 0 through 9 and that a linear prediction analysis is made for each digit utterance. A single utterance of the digit 1, for example, may result in a sequence of acoustic feature signals ##EQU5## for n1 time frames. Each acoustic feature signal O is a multidimensional linear prediction coefficient (LPC) vector well known in the art. Alternatively, cepstral or other features may be used. The acoustic feature sequences for a large number of such utterances of all digits are stored for use in forming Markov model templates. The speech pattern storing operation is indicated in step 301. An initial Markov model is then generated for a selected digit as per step 305. The Markov model may be selected arbitrarily, or may correspond to a previously used Markov model template that is to be improved. The model for word r comprises a prescribed set of transition probability matrix signals Ar =[ar ij ] and a prescribed set of output symbol probability signals derived from a Markov model ##EQU6## corresponding to a multivariate Gaussian function where M is the number of mixture components, N is the number of states, and D is the number of dimensions of the feature vector for each frame.

The feature signals O for the selected digit are then combined with the current Markov model signals to produce the best state sequence of feature signals according to the current Markov model for the digit as per step 310. This is accomplished by assigning feature signal frames to the states of the Markov model in FIG. 1 using standard Viterbi matching techniques such as described in the aforementioned article, "On the Application of Vector Quantization and Hidden Markov Models to Speaker-Independent, Isolated Word Recognition", by L. R. Rabiner et al, so that a maximum likelihood score is obtained.

Such a procedure is illustrated as follows. Each frame sequence of feature signals for an utterance of the selected digit is applied to the current model and all possible paths of the frames through the states of the model are evaluated to determine the path having the maximum likelihood. Given the current model λr and the observation sequence O of frame feature signal, the scoring procedure may be stated as ##EQU7## The frames of the selected digit are then sorted according to the optimum state sequence so that a set of LPC vector signal frames are assigned to each state of the Markov model as per step 315. This procedure is repeated for each of the words in the training set for digit r. When finished, for each state, the LPC feature vector signals of the Q frames of all the selected digit utterances assigned to the state are clustered into M groups using a clustering procedure as per step 320. The clustering procedure disclosed in the article "Considerations in applying clustering techniques to speaker-independent word recognition", by L. R. Rabiner and J. G. Wilpon, in Journal of the Acoustical Society of America, 66(3), September 1979, pp. 663-673, or other clustering arrangements may be used.

Signals corresponding to a new Markov model are formed from the clustered vector signals of step 320 in step 325. The new cmj coefficients are produced in accordance with ##EQU8## The new mean signals μmjk are formed according to ##EQU9## where r(p)=m corresponds to the pth vector, FS(p), being in cluster m, and [FS(p)]k corresponds to the kth component of vector FS(p), and the new covariance signals σmjk are generated using ##EQU10## where m is the mth cluster and k is the kth component of the LPC feature vector signal. The loop from steps 315 to 325 is iterated over the set of states 1 to N of the selected digit.

At this point, the current Markov model has been used to form a next succeeding Markov model of the selected digit characterized by the cmj coefficient signals, the μmjk mean signals and the σmjk covariance signals of equations (10), (11) and (12). It can be rigorously shown that the successive Markov models formed by this method are convergent. In accordance with the invention, a signal corresponding to each Markov model is formed so that the models can be compared quantitatively until the difference between successive Markov models is less than a predetermined value.

Model comparison is done by generating frame sequences of feature signal vectors from the current and next successive Markov models. In the formation of a sequence of feature signal vectors, the model begins in state i=1. An observation frame vector, O, is randomly chosen according to the probability curve b1 (O) (waveform 210 of FIG. 2) for the model. A transition probability is then randomly selected and the state transition given by a1j is made. The resulting transition puts the model into state i (e.g., j=1,2,3). A feature signal vector, O, is then randomly generated according to the probability bj (O), and another feature state transition is generated. This Monte Carlo type procedure is continued to produce a sequence of feature signal vectors and the likelihood of occurrence of the sequence is determined in accordance with equation (1) for the current Markov model λ. The procedure is repeated for the a and b probability signals of the next successive Markov model λ. Signals corresponding to the likelihood of the set of feature vectors L(O|λ) and L(O|λ) for models λ and λ are produced (step 335) and compared (step 340) by means of a distance signal ##EQU11## where T is the total number f frame feature observations generated by the model. If the Markov model distance signal of step 335 is greater than a predetermined value ε, the just produced Markov model signals are stored as the input Markov model (step 350) for the next iteration and step 310 is reentered for another iteration of the Markov model generation loop from step 310 to step 340.

When the Markov model difference signal is reduced below ε, step 345 is entered and the Markov model signals formed in the last iteration of the Markov model generation loop is reestimated to improve its accuracy. The reestimation is performed in accordance with the well-known Baum method described in the article, "An Inequality and Associated Maximization Technique in Statistical Estimation for Probabilistic Functions of Markov Processes", by L. E. Baum, appearing in Inequalities-III, pp. 1-8, 1972. More particularly, for a set of S training versions of a word, a likelihood signal ##EQU12## is iteratively generated for the frame feature observation sequences of the selected digit from store 715 ##EQU13## where Ot.sup.(s) is a D-dimensional feature signal vector for 1≦s≦S, 1≦t≦Ts.

α.sub.t.sup.(s) (j)=L(O.sub.1.sup.(s) O.sub.2.sup.(s) . . . O.sub.t.sup.s and j|λ)                    (16)

is the forward partial likelihood of the first t observations of observation sequence O based on the current Markov model that ends in state j and λ is the current model. The observation sequence may be provided by the input utterances of the digit from one or more speakers.

The successive values of the likelihood signal L are compared in accordance with ##EQU14## where L is the previously generated likelihood signal, and L is the currently generated likelihood signal. The iterations are continued until this condition is satisfied or a predetermined number of iterations has been performed. Each time the inequality of equation (17) is not met, the signals of the Markov model aij, cjm, μjm, and σjm are modified and a new value of the likelihood signal is formed. It can be shown that the estimating procedure converges so that the values of the Markov model parameter signals at the end of each iteration provide improved accuracy. The modification of the parameter signals in each iteration is performed in accordance with the following: ##EQU15## where 1,j≦N, 1≦m≦M ##EQU16## After the comparison of successive likelihood values in step 340 provides a signal less than θ or a prescribed number of iterations have been performed, the Markov model signals corresponding to the last likelihood signal are stored as the template for the current digit.

DETAILED DESCRIPTION

FIGS. 4, 5 and 6 show detailed flow charts illustrating the formation of Markov model templates in accordance with the invention, and FIG. 7 is a block diagram of a processing circuit that may be used to implement the method of FIGS. 4, 5 and 6. Referring to FIG. 7, identified utterances are received at electroacoustic transducer 701, and electrical signals produced by the transducer responsive to each utterance are applied to acoustic feature sequence generator 705. The feature generator is operative to perform a linear prediction analysis of the input utterance from which a sequence of LPC coefficient vector signals characteristic of the utterance is obtained. The vector signal sequence is transferred to acoustic feature sequence store 715 via interface 710 and bus 735. Feature sequence generator 705 may comprise a microprocessor such as the type MC68000 manufactured by Motorola Inc., and described in the publication MC68000 16 Bit Microprocessor User's Manual, second edition, Motorola Inc., 1980.

The LPC vector signal sequences from feature signal generator 705 may represent the utterances of identified digits of one or more speakers and provide a sufficient data base of speech feature signals for the digits to form Markov models therefrom. FIG. 8 illustrates the manner in which the digit vector signal sequences are stored. Each entry into store 715 comprises the frame sequence of feature vector signals O1, O2, . . . , OT.sbsb.i resulting from the digit utterance, a signal wi identifying the digit that is spoken and a signal Ti corresponding to the number of frames in the digit utterance. The first entry, for example, is a sequence of Ti frame LPC vector signals O1, O2, . . . , OT.sbsb.i, the digit identification w1 and the number of frames signal Ti. The entries may be stored in any order and are addressable by digit identification codes wi.

Signal processor 725 is adapted to perform the operations required by the flow charts of FIGS. 4-6 to form the Markov model templates under control of the permanently stored instructions in speech pattern template forming program store 720. The resulting Markov model templates are transferred to template store 728 and are supplied therefrom to utilization device 740. Device 740 may be an automatic speech recognizer that may be of the type illustrated in FIGS. 13 and 14 or may be a device adapted to permanently store Markov model templates for use in speech recognition equipment. Processor 725 may be a general purpose data processor well known in the art or may be a microprocessor such as the MC68000. Alternatively, processor 725, bus 735, program store 720, and random access memories 715 and 728 may be the type OB68K1A MC68000/MULTIBUS single board computer manufactured by Omnibyte Corporation, West Chicago, Ill. A Q bus arrangement could also be used. Store 720 may comprise a read-only type memory permanently storing instructions that implement the steps shown in the flow charts of FIGS. 4-6. These instructions are listed in FORTRAN language form in Appendix A hereto.

Referring to the flow chart of FIG. 4, the frame sequence of acoustic feature signals is generated in feature signal generator 705 for identified spoken digit patterns DL and the LPC feature signals therefrom are placed in successive positions of store 715 as per step 401. When Lmax patterns, e.g., 1000, have been analyzed and the feature signal sequences therefor have been stored, the initial Markov model is produced (step 405) and stored in template store 728. Alternatively, Markov model signals may have been previously stored in template store 728. The speech pattern (digit) index is set to r=1 in step 410 and the Markov model template formation process is started in step 415 for the currently selected digit pattern. The initial Markov model signals for the current digit are obtained from the template store. This initial set of signals may be arbitrarily selected, e.g., aij =1/3 for j=i, i+1, i+2; i=1, 2, . . . , N-2, aN-1,N =1/2, aN-1,N-1 =1/2, aNN =1.0; all other aij =0, Cmj =1/M, μmj =0, σmj =1, or may comprise previously formed template signals which are to be improved through the use of a different or expanded data base of utterance feature signals.

Steps 420 through 465 are operations directed to aligning the frame sequences of stored feature signals for the current digit with the current Markov model λr and assigning the feature signal frames to the states of the model. At the beginning of the alignment, the frame store index FS(n,p) and the frame count index CS(n) are set to zero for the count sequence p=1, 2, . . . , PM, e.g., PM=5000, and the Markov model state sequence n=1, 2, . . . , N (step 420). The count and word token indices p and L are set to 1 (step 425) and the feature signals corresponding to f(L,j), TL, and WL for digit pattern DL are supplied from store 715 to signal processor 725 via bus 735.

The digit utterance entries in store 715 are read by processor 725 in step 430 and the digit identification code WL is compared to the current digit being processed (step 435). If the feature signal sequence corresponds to the current digit being processed, step 440 is entered in which the feature signal frames of the entry are aligned with the current Markov model λr through use of equations (7), (8) and (9). A flow chart detailing the alignment process is shown in FIG. 9.

In general, the flow chart of FIG. 9 follows equations (8), (9), and (10) and shows the operations of signal processor 725 in forming a signal τ (N) for each sequence of feature vector observation signals and signals γ(i) representative of the most probable path through the states of the Markov model shown in FIG. 1. The arrangement of FIG. 9 applies the transition probability signals aij and the observation probability signals bj (Ot) of the current Markov model λr to the frames t of the feature signal frame sequences stored in acoustic feature store 715 to sort the feature signal frames into states. The resulting sorted frames are then stored in state frame store 728.

Referring to FIG. 9, step 901 is entered from decision step 435, and the initial probability signal for the first state (i=1) is generated. The state index is then set to 1 (step 905) and the loop including steps 907, 909, and 911 is iterated for states 2, 3, . . . , N to initially set the probability signals σ1 (i) to -∞ and the frame state path signals γ1 (i) to 0.

After the probability and path signals for state N have been reset, the sequence frame index is set to 1 and incremented in steps 913 and 915. Steps 915 through 940 correspond to equations (8) and (9) in which the probability of each feature observation frame sequence is evaluated, and the paths for the sequence based on the current Markov model are determined. The evaluation is done through the range of feature signal observation frames from frame t=2 to the last frame TL as indicated in decision step 917. Until frame TL has been processed, each destination state j in the range between j=1 to j=N is selected (steps 920, 922 and 924). For each destination state j, the source states i in the permitted range max(1,j-2)≦i≦j are sequentially selected (steps 927 and 929) and a signal representative of the probability of the feature signal observation sequence following the path given in step 935 is generated.

The maximum probability path signal for equation (9) is selected in steps 937 and 940. When i>j (step 931), the maximum probability signal σt (j) is stored for state j (step 945). The loop from step 922 to 945 is iterated through the destination states 1≦j≦N so that all possible frame state paths for the frames from t=2 to t=TL are traversed. When t>TL, the probability signal formation is complete and step 950 is entered from decision step 917.

Signals q(t) in the flow chart of FIG. 9 represent the maximum likelihood estimates of the states of the feature observation frames based on the current Markov model. Estimated state signal q(TL) is initially set to last state N in step 950 and the frame index t is set to the last frame TL of the feature observation sequence in step 955. The loop from step 960 to step 975 is then iterated so that the frames γt (q(t)) of the observation sequence obtained in step 940 in the frame state path probability signal formation are sorted according to state (step 960) and stored in frame state store 738 (step 965). The probability signal and back track processing of FIG. 9 are performed in signal processor 725 as controlled by the instructions stored in program store 720 listed in FORTRAN language in Appendix B hereto.

After the alignment and sorting process of step 440 is completed, the frames of the digit entry feature signals have been assigned to the states q(j) of model λr. The frame index j is set to 1 (step 450) and the loop including steps 455, 460 and 465 is iterated through the speech pattern frames. As per step 455, the feature signal vector observation f(L,j) of each frame is stored as signal FS(q(j),p) in state frame store 738 as addressed by Markov model state and the count of frames signal CS(q(j)) in each state is incremented. The count and frame indices p and j are incremented in step 460, and the frame to be processed is tested to determine whether all entry frames have been sorted (step 465). When j is greater than TL, step 467 is entered in which the entry index L is incremented. Until entry index L is greater than the last entry number Lmax, the entries in store 715 are successively addressed in step 430, and the frames of the entries corresponding to the current digit being processed are sorted as per steps 440 through 465.

When the last entry for the current digit has been processed according to the flow chart of FIG. 4, the feature signal frames for all digit entries have been sorted into states in accordance with the current Markov model signals. FIG. 10 illustrates the arrangement of feature signals in frame state store 738. The frames assigned to state 1 are sequentially identified in store locations addressed by state 1, and the number of state 1 frames CS(1) is inserted at the end of the state 1 sequence. The frame assignments for the other states of model λr are similarly stored in store 738.

The flow chart of FIG. 5 illustrates the operation of processor 725 in separating the frame feature signals of each state of frame state store 738 into clusters and generating a new set of Markov model signals cmj, μmjk, and σmjk from the clustered feature signals. Step 501 is entered from step 469 of FIG. 4 and state index n and the total number of feature vector signals Q are set to 1 and CS(n) in steps 501 and 505, respectively. The Q feature signal vectors in the nth state stored in frame-state store 738 are sorted into M clusters as per step 510 using the vector quantization clustering algorithm described in the article, "Distortion Performance of Vector Quantization for LPC Voice Coding", by Bing-Hwang Juang, David Y. Wong and Augustine H. Gray, Jr., appearing in the IEEE Transactions on Acoustics, Speech and Signal Processing, Vol. ASSP-30, No. 2, April 1982, pp. 294-303. The clustering is performed by signal processor 725 under control of program store 720. The permanently stored instructions for the clustering in the program store are set forth in FORTRAN language form in Appendix C hereto.

Subsequent to the clustering of the nth state feature signals, the parameters for the next successive Markov model, cmj, μmjk, and σmjk, are generated according to step 515. The cluster index m is incremented in step 520 and the occurrence of the last cluster M is checked in step 525. When the last cluster has been processed, the state index n is incremented (step 530) and the occurrence of the last state N is checked in step 535. Until state N clustering and Markov model parameter formation are complete, steps 505 through 535 are iteratively performed for the sequence of states 1, 2, . . . , N.

After all Markov model signals have been formed in accordance with FIG. 5, the current Markov model λr and next succeeding Markov model λr are compared through the operations of the flow chart of FIG. 6. Step 605 of FIG. 6 is entered from step 535 of FIG. 5 and a set of K observation signal sequences ##EQU17## each with sequence duration

T=T.sub.k from k=1 to K                                    (25)

and with total duration ##EQU18## are generated from the current Markov model λr. The feature signal observations of each frame sequence are produced through random selection of observation vectors using the observation vector probabilities b and random selection of the transition probabilities a of the model λr. A detailed flow chart illustrating the observation sequence formation of step 605 is shown in FIG. 11. The instructions in store 720 for step 605 are listed in FORTRAN language form in Appendix D.

Initially, FIG. 11 is entered from step 535 in FIG. 5, and the feature signal observation count index q as well as the model state index i are set to 1 in steps 1101 and 1105. The final state duration count n is set to 0 and the observation time index t is set to 1 in steps 1110 and 1115. An observation vector signal representative of an LPC vector feature signal is produced by randomly selecting an observation O according to the probability function bi (O) of the multivariate Markov model λr as per step 1120. A transition to the next state j is made based on those transitions permitted by the model and the probability of each permitted transition (step 1125). For the left-to-right Markov models, only transitions to the current and next two states are allowable. The current state i becomes the destination state j of step 1125 in step 1130. As long as current state i is not the final state N (step 1135), the time index is incremented (step 1142) and feature signal observation symbol generating step 1120 is reentered. When the final state N is reached (step 1135), state duration index n is incremented (step 1140) and observation symbol generation is iterated in the loop, including steps 1120, 1125, 1130, 1135, 1140, 1142, and 1145 until the state duration count reaches a predetermined value (step 1145). At that time, the observation sequence count is increased (step 1150), and the next observation sequence is formed via step 1105. After the K sequences have been generated and stored, the observation symbol sequence formation shown in FIG. 11 is performed for Markov model λr by changing the a and b model parameter signals in the steps of FIG. 11. Step 610 of FIG. 6 is then entered from step 1155 of FIG. 11.

At this point in the template generation process, a set of observation sequences based on model λr and a set of observation sequences based on model λr have been generated and stored. Since the succession of Markov models produced in accordance with the invention are convergent, a comparison of the current and immediately succeeding models shows whether an improvement in the modeling has occurred. When the improvement is below a predetermined threshold ε, the immediately succeeding model λr is accepted as the template for the selected speech pattern.

In step 610, a signal L(O|λr) representative of the probability that an observation sequence has been generated by Markov model λr is produced in accordance with equation (1). A signal L(O|λr) is also formed, and the similarity between the model probabilities is evaluated through a distance measure of equation (14) as per step 615. If the distance measure d(λr, λr) is not lower than a threshold ε, model λr is not considered a sufficiently accurate approximation for use as a reference pattern template. In this event, output model λr becomes current input model λr, and control is transferred to step 420 of FIG. 4 for the formation of a new successive output model λr. When the similarity between models λr and λr in step 620 is better than threshold ε, the output Markov model signals λr are reestimated in step 625 to obtain the best Markov model approximation.

The reestimation method is illustrated in the flow chart of FIG. 12, and the instructions in store 720 to perform the functions in FIG. 12 are shown in Appendix E. Referring to FIG. 12, the likelihood signal L is initially set to 0 in step 1201, and the reestimation iteration index i1 is reset to 1 in step 1203. The likelihood signal of the current iteration is generated as per step 1210 using the relationship of equation (15) for αTs given in equation (16) after index i1 is compared to iteration limit I1 (step 1205). The likelihood signal of the preceding iteration L is then compared to the current iteration likelihood signal L as per step 1215. As long as the relationship of step 1215 is not satisfied, the Markov model parameter signals are modified in steps 1220, 1225, 1230, and 1235 in accordance with equations (18), (19), (20) and (21) so that more accurate Markov model parameters may be formed.

In step 1220, the numerator represents the expected number of transitions from state i to state j for the observation sequence O, and the denominator corresponds to the expected number of transitions out of state i. The ratio is an estimate of the transition probability aij as per equation (18). Step 1225 provides an estimate of the mth mixture coefficient, cjm, of the jth state according to equation (19) which is obtained from the ratio of the expected number of observations from the mth term of the mixture for the jth state and the expected number of observations in the jth state.

Step 1230 corresponds to mean value μjm of the observations of equation (20) and is formed from the ratio of the expected value of feature observations over the entire observation sequence O to the likelihood of a feature observation coming from the mth mixture term in state j. In like manner, the variance σjm of the observations in step 1235 corresponds to equation (21) and is formed by taking the ratio of the expected value of the variance of feature observations to the likelihood that a feature observation comes from the mth mixture term in state j.

Subsequent to the modifications of the Markov model parameter signals of the current iteration in steps 1220 through 1235, the model parameter signals of the preceding iteration are replaced by those obtained in the current iteration (step 1240). The iteration index i1 is then incremented in step 1245, and decision step 1205 is reentered. Since the Markov model parameter signals of succeeding iterations are convergent, the ratio of succeeding likelihood signals L and L approaches unity as the iteration index count increases.

When the condition of step 1215 is satisfied or I1 iterations have been completed, the Markov model reestimation for the current digit template is completed, and the model signals are stored in template store 728 of FIG. 7 (step 1250). After the Markov model signals for the rth template have been reestimated as per the steps of FIG. 12, step 630 is then entered from step 1250, and the digit index r is incremented therein. The incremented index is tested as the last speech pattern template in step 635. The Markov model template formation for the successive speech patterns is continued as per the flow charts of FIGS. 4, 5, and 6 until the last speech pattern template I is placed in store 728. The Markov model templates for the speech pattern vocabulary may then be transferred to utilization device 740 via bus 735 and interface 730.

A set of Markov model signals is generated for each reference pattern to be recognized and stored in a reference pattern Markov model store of a speech recognizer such as shown in FIG. 13. The reference patterns may, for example, be the spoken digits 0 through 9. When the recognizer receives a speech pattern input at microphone 1310, it operates in accordance with the flow chart of FIG. 14 to provide a signal r* that identifies the spoken digit of the input speech pattern. In FIG. 13, the reference pattern Markov model signal sets are permanently stored in read-only memory 1360, and the operation of the recognizer set forth in FIG. 14 is controlled by the permanently stored instructions in control program store 1355. Feature signal generator 1330 may comprise a microprocessor such as type MC68000 manufactured by Motorola Inc., having permanently stored instructions to control feature signal generation and endpoint detection well known in the art. Processor 1340, bus 1345, control memory 1350 and RAM 1355 may be the type OB68K1A MC68000/MULTIBUS single board computer manufactured by Omnibyte Corporation, West Chicago, Ill. A Q bus arrangement could also be used.

Referring to FIGS. 13 and 14, step 1407 is entered from step 1405 when the recognizer is available to process a new speech pattern input at transducer 1300. The speech pattern is converted into a sequence of digital codes representative of the successive speech samples of the pattern in filter and sample circuit 1310 and analog-to-digital converter 1320 as is well known in the art as per steps 1407 and 1409. Responsive to the digital codes from converter 1320, a sequence of speech pattern feature signals is generated in LPC feature signal generator and endpoint detector 1130 (step 1411) and transferred to feature signal store 1370.

When the end of the pattern is detected (step 1418), the Markov model signal set of the first stored reference pattern is selected (step 1425) in processor circuit 1340 in accordance with the programmed instructions of control program store 1355. The speech pattern feature signals from feature signal store 1370 are combined with the selected Markov model signal set from store 1360 in processor 1340 to form a signal representative of the likelihood that the speech pattern corresponds to the selected reference pattern (step 1430). The loop including steps 1425, 1430 and 1435 is iterated through all reference pattern Markov model signal sets so that a likelihood signal is stored for each reference pattern. The reference pattern having the maximum likelihood signal is selected in step 1440, and the reference pattern index signal identifying the input speech pattern is produced by processor 1340 in step 1445. Control is then returned to step 1405 for recognition of subsequent speech patterns.

The invention has been shown and described with reference to a particular embodiment thereof. It is to be understood, however, that various modifications and changes in form and detail may be made by those skilled in the art without departing from the spirit and scope of the invention. ##SPC1##

Claims (8)

What is claimed is:
1. A method for analyzing speech comprising the steps of:
generating speech pattern reference templates, including, for each such template, the steps of:
a. analyzing at least one identified speech pattern to generate a frame sequence of acoustic feature signals representative thereof:
b. generating a first set of signals representative of a state-transitional (Markov) model of said identified speech pattern;
c. producing a speech pattern template responsive to the current state-transitional model and the said frame sequence of acoustic feature signals; and
d. iterating steps b and c, including with respect to step b
matching the continuously valued characteristics of the model to the observation measurements to produce a continuous-probability-density function; and with respect to step c grouping the feature signals of the speech patterns into related clusters corresponding to states of the previous state-transitional model, whereby with further grouping of the feature signals the continuous probability density function acquires components representing a mixture of different continuous probability density functions and the speech pattern template becomes the speech pattern reference template.
2. A method for analyzing speech according to claim 1 wherein said probability density signals comprise a signal representative of the mean value of sorted acoustic feature signals in each cluster of each state and a set of signals representative of covariance matrix values forming a mixture multivariate continuous probability density function for sorted acoustic feature signals in each cluster of each state.
3. A method for analyzing speech according to claim 2 wherein the iterating step includes
forming a first signal corresponding to the likelihood of occurrence of the sequences of acoustic feature signals of the identified speech patterns from said previous state-transitional (Markov) model signal set;
forming a second signal corresponding to the likelihood of occurrence of the sequences of acoustic features of the identified speech patterns from the current iteration state-transitional (Markov) model signal set; and
generating a signal representative of the correspondence between said first and second likelihood signals.
4. The method for recognizing an unknown utterance as one of a plurality of stored reference patterns each comprising a set of signals representative of a Markov model of an identified speech pattern comprising the steps of:
forming a time frame sequence of acoustic feature signals representative of the unknown utterance;
generating a signal representative of the likelihood of the unknown speech pattern being each reference pattern jointly responsive to said sequence of acoustic feature signals of the speech pattern and the Markov model signals of each reference pattern; and
identifying the unknown utterance as one of the reference patterns responsive to said probability representative signals;
said Markov model signals being formed by the the method of claim 1.
5. The method for recognizing an unknown utterance according to claim 4 wherein the iterating step involved in forming the reference template further comprises:
forming a first signal corresponding to the likelihood of occurrence of the sequences of acoustic feature signals of the identified speech patterns from the previous state-transitional (Markov) model signal set;
forming a second signal corresponding to the likelihood of occurrence of the sequences of acoustic features of the identified speech pattern from the current iteration state-transitional (Markov) model signal set; and
generating a signal representative of the correspondence between said first and second likelihood signals.
6. The method for recognizing an unknown utterance according to claim 5 wherein said step of forming the current iteration Markov model signal set involved in forming the reference template further comprises:
sorting the acoustic feature signals of said speech patterns into states of the previous state-transitional (Markov) model
sorting the acoustic feature signals of said speech patterns into states of the previous Markov model responsive to the previous Markov model signal set and the acoustic feature signal sequences of the identified speech patterns; and
said current iteration Markov model forming step comprises forming signals representative of the probability density of occurrence of acoustic features responsive to the sorted acoustic feature signal sequences of the speech patterns and the previous Markov model signal set.
7. The method for recognizing an unknown utterance according to claim 6 wherein said probability density signals comprise a signal representative of the mean value of said sorted acoustic feature signals in each cluster of each state and a set of signals representative of covariance matrix values forming a mixture multivariate continuous probability density function for sorted acoustic feature signals in each cluster of each state.
8. A speech recognizer for recognizing an unknown utterance comprising:
means for storing a plurality of reference patterns each comprising a set of signals representative of a state-transitional (Markov model) of an identified speech pattern;
means for forming a time frame sequence of acoustic feature signals representative of the unknown utterance;
means jointly responsive to said sequence of acoustic feature signals of the utterance and the constrained Markov model signals of the reference patterns for generating a signal representative of the likelihood of the unknown speech pattern being each reference pattern; and
identifying the unknown utterance as one of the reference patterns responsive to said likelihood representative signals;
wherein said templates stored in the means for storing speech pattern reference templates are generated by the method of claim 4;
the time frame sequence forming means being adapted to render said time frame sequence to be suitable for comparison with said templates.
US06714517 1985-03-21 1985-03-21 Hidden Markov model speech recognition arrangement Expired - Lifetime US4783804A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US06714517 US4783804A (en) 1985-03-21 1985-03-21 Hidden Markov model speech recognition arrangement

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
US06714517 US4783804A (en) 1985-03-21 1985-03-21 Hidden Markov model speech recognition arrangement
FR8603987A FR2579357B1 (en) 1985-03-21 1986-03-20 Method and speech analysis device by Markov model hides
JP6103786A JPH0555040B2 (en) 1985-03-21 1986-03-20

Publications (1)

Publication Number Publication Date
US4783804A true US4783804A (en) 1988-11-08

Family

ID=24870357

Family Applications (1)

Application Number Title Priority Date Filing Date
US06714517 Expired - Lifetime US4783804A (en) 1985-03-21 1985-03-21 Hidden Markov model speech recognition arrangement

Country Status (3)

Country Link
US (1) US4783804A (en)
JP (1) JPH0555040B2 (en)
FR (1) FR2579357B1 (en)

Cited By (148)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4852180A (en) * 1987-04-03 1989-07-25 American Telephone And Telegraph Company, At&T Bell Laboratories Speech recognition by acoustic/phonetic system and technique
US4918731A (en) * 1987-07-17 1990-04-17 Ricoh Company, Ltd. Speech recognition method and apparatus
WO1990009644A1 (en) * 1989-02-07 1990-08-23 Smiths Industries Public Limited Company Monitoring
US5029212A (en) * 1988-10-03 1991-07-02 Nec Corporation Continuous speech recognition unit using forward probabilities
US5031217A (en) * 1988-09-30 1991-07-09 International Business Machines Corporation Speech recognition system using Markov models having independent label output sets
US5072452A (en) * 1987-10-30 1991-12-10 International Business Machines Corporation Automatic determination of labels and Markov word models in a speech recognition system
US5075896A (en) * 1989-10-25 1991-12-24 Xerox Corporation Character and phoneme recognition based on probability clustering
US5119425A (en) * 1990-01-02 1992-06-02 Raytheon Company Sound synthesizer
US5129002A (en) * 1987-12-16 1992-07-07 Matsushita Electric Industrial Co., Ltd. Pattern recognition apparatus
US5148489A (en) * 1990-02-28 1992-09-15 Sri International Method for spectral estimation to improve noise robustness for speech recognition
US5233681A (en) * 1992-04-24 1993-08-03 International Business Machines Corporation Context-dependent speech recognizer using estimated next word context
DE4241688A1 (en) * 1992-03-21 1993-09-23 Atr Interpreting Telephony Res Generating sub-word model for speech recognition - successively dividing conditions in original model into temporal and contextual domains to form hidden Markow network using max. likelihood method
WO1994000836A1 (en) * 1992-06-29 1994-01-06 Kurzweil Applied Intelligence, Inc. Speech regognition system utilizing vocabulary model preselection
US5289562A (en) * 1990-09-13 1994-02-22 Mitsubishi Denki Kabushiki Kaisha Pattern representation model training apparatus
US5293451A (en) * 1990-10-23 1994-03-08 International Business Machines Corporation Method and apparatus for generating models of spoken words based on a small number of utterances
US5307444A (en) * 1989-12-12 1994-04-26 Matsushita Electric Industrial Co., Ltd. Voice analyzing system using hidden Markov model and having plural neural network predictors
US5333236A (en) * 1992-09-10 1994-07-26 International Business Machines Corporation Speech recognizer having a speech coder for an acoustic match based on context-dependent speech-transition acoustic models
US5377301A (en) * 1986-03-28 1994-12-27 At&T Corp. Technique for modifying reference vector quantized speech feature signals
US5390278A (en) * 1991-10-08 1995-02-14 Bell Canada Phoneme based speech recognition
US5450523A (en) * 1990-11-15 1995-09-12 Matsushita Electric Industrial Co., Ltd. Training module for estimating mixture Gaussian densities for speech unit models in speech recognition systems
US5452397A (en) * 1992-12-11 1995-09-19 Texas Instruments Incorporated Method and system for preventing entry of confusingly similar phases in a voice recognition system vocabulary list
US5502790A (en) * 1991-12-24 1996-03-26 Oki Electric Industry Co., Ltd. Speech recognition method and system using triphones, diphones, and phonemes
US5509104A (en) * 1989-05-17 1996-04-16 At&T Corp. Speech recognition employing key word modeling and non-key word modeling
US5526465A (en) * 1990-10-03 1996-06-11 Ensigma Limited Methods and apparatus for verifying the originator of a sequence of operations
US5535305A (en) * 1992-12-31 1996-07-09 Apple Computer, Inc. Sub-partitioned vector quantization of probability density functions
US5544257A (en) * 1992-01-08 1996-08-06 International Business Machines Corporation Continuous parameter hidden Markov model approach to automatic handwriting recognition
US5596680A (en) * 1992-12-31 1997-01-21 Apple Computer, Inc. Method and apparatus for detecting speech activity using cepstrum vectors
US5598507A (en) * 1994-04-12 1997-01-28 Xerox Corporation Method of speaker clustering for unknown speakers in conversational audio data
US5606643A (en) * 1994-04-12 1997-02-25 Xerox Corporation Real-time audio recording system for automatic speaker indexing
US5606644A (en) * 1993-07-22 1997-02-25 Lucent Technologies Inc. Minimum error rate training of combined string models
US5623609A (en) * 1993-06-14 1997-04-22 Hal Trust, L.L.C. Computer system and computer-implemented process for phonology-based automatic speech recognition
US5625747A (en) * 1994-09-21 1997-04-29 Lucent Technologies Inc. Speaker verification, speech recognition and channel normalization through dynamic time/frequency warping
US5649057A (en) * 1989-05-17 1997-07-15 Lucent Technologies Inc. Speech recognition employing key word modeling and non-key word modeling
US5664058A (en) * 1993-05-12 1997-09-02 Nynex Science & Technology Method of training a speaker-dependent speech recognizer with automated supervision of training sufficiency
US5682501A (en) * 1994-06-22 1997-10-28 International Business Machines Corporation Speech synthesis system
US5682464A (en) * 1992-06-29 1997-10-28 Kurzweil Applied Intelligence, Inc. Word model candidate preselection for speech recognition using precomputed matrix of thresholded distance values
US5692104A (en) * 1992-12-31 1997-11-25 Apple Computer, Inc. Method and apparatus for detecting end points of speech activity
US5719996A (en) * 1995-06-30 1998-02-17 Motorola, Inc. Speech recognition in selective call systems
US5787198A (en) * 1992-11-24 1998-07-28 Lucent Technologies Inc. Text recognition using two-dimensional stochastic models
US5794198A (en) * 1994-10-28 1998-08-11 Nippon Telegraph And Telephone Corporation Pattern recognition method
US5799277A (en) * 1994-10-25 1998-08-25 Victor Company Of Japan, Ltd. Acoustic model generating method for speech recognition
US5806030A (en) * 1996-05-06 1998-09-08 Matsushita Electric Ind Co Ltd Low complexity, high accuracy clustering method for speech recognizer
US5806029A (en) * 1995-09-15 1998-09-08 At&T Corp Signal conditioned minimum error rate training for continuous speech recognition
US5819222A (en) * 1993-03-31 1998-10-06 British Telecommunications Public Limited Company Task-constrained connected speech recognition of propagation of tokens only if valid propagation path is present
US5825978A (en) * 1994-07-18 1998-10-20 Sri International Method and apparatus for speech recognition using optimized partial mixture tying of HMM state functions
US5832430A (en) * 1994-12-29 1998-11-03 Lucent Technologies, Inc. Devices and methods for speech recognition of vocabulary words with simultaneous detection and verification
US5835890A (en) * 1996-08-02 1998-11-10 Nippon Telegraph And Telephone Corporation Method for speaker adaptation of speech models recognition scheme using the method and recording medium having the speech recognition method recorded thereon
US5848130A (en) * 1996-12-31 1998-12-08 At&T Corp System and method for enhanced intelligibility of voice messages
US5848388A (en) * 1993-03-25 1998-12-08 British Telecommunications Plc Speech recognition with sequence parsing, rejection and pause detection options
US5865626A (en) * 1996-08-30 1999-02-02 Gte Internetworking Incorporated Multi-dialect speech recognition method and apparatus
US5950158A (en) * 1997-07-30 1999-09-07 Nynex Science And Technology, Inc. Methods and apparatus for decreasing the size of pattern recognition models by pruning low-scoring models from generated sets of models
US5960395A (en) * 1996-02-09 1999-09-28 Canon Kabushiki Kaisha Pattern matching method, apparatus and computer readable memory medium for speech recognition using dynamic programming
US5963902A (en) * 1997-07-30 1999-10-05 Nynex Science & Technology, Inc. Methods and apparatus for decreasing the size of generated models trained for automatic pattern recognition
US5991442A (en) * 1995-05-10 1999-11-23 Canon Kabushiki Kaisha Method and apparatus for pattern recognition utilizing gaussian distribution functions
US6047256A (en) * 1988-02-09 2000-04-04 Nec Corporation Device for generating a reference pattern with a continuous probability density function derived from feature code occurrence probability distribution
US6049594A (en) * 1995-11-17 2000-04-11 At&T Corp Automatic vocabulary generation for telecommunications network-based voice-dialing
US6061654A (en) * 1996-12-16 2000-05-09 At&T Corp. System and method of recognizing letters and numbers by either speech or touch tone recognition utilizing constrained confusion matrices
US6122612A (en) * 1997-11-20 2000-09-19 At&T Corp Check-sum based method and apparatus for performing speech recognition
US6137863A (en) * 1996-12-13 2000-10-24 At&T Corp. Statistical database correction of alphanumeric account numbers for speech recognition and touch-tone recognition
US6141661A (en) * 1997-10-17 2000-10-31 At&T Corp Method and apparatus for performing a grammar-pruning operation
US6154579A (en) * 1997-08-11 2000-11-28 At&T Corp. Confusion matrix based method and system for correcting misrecognized words appearing in documents generated by an optical character recognition technique
US6157731A (en) * 1998-07-01 2000-12-05 Lucent Technologies Inc. Signature verification method using hidden markov models
US6205261B1 (en) 1998-02-05 2001-03-20 At&T Corp. Confusion set based method and system for correcting misrecognized words appearing in documents generated by an optical character recognition technique
US6205428B1 (en) 1997-11-20 2001-03-20 At&T Corp. Confusion set-base method and apparatus for pruning a predetermined arrangement of indexed identifiers
US6208965B1 (en) 1997-11-20 2001-03-27 At&T Corp. Method and apparatus for performing a name acquisition based on speech recognition
US6219453B1 (en) 1997-08-11 2001-04-17 At&T Corp. Method and apparatus for performing an automatic correction of misrecognized words produced by an optical character recognition technique by using a Hidden Markov Model based algorithm
US6230128B1 (en) 1993-03-31 2001-05-08 British Telecommunications Public Limited Company Path link passing speech recognition with vocabulary node being capable of simultaneously processing plural path links
US6246980B1 (en) * 1997-09-29 2001-06-12 Matra Nortel Communications Method of speech recognition
US6269334B1 (en) * 1998-06-25 2001-07-31 International Business Machines Corporation Nongaussian density estimation for the classification of acoustic feature vectors in speech recognition
US6400805B1 (en) 1998-06-15 2002-06-04 At&T Corp. Statistical database correction of alphanumeric identifiers for speech recognition and touch-tone recognition
US6434522B1 (en) * 1992-06-18 2002-08-13 Matsushita Electric Ind Co Ltd Combined quantized and continuous feature vector HMM approach to speech recognition
US20030067467A1 (en) * 2001-03-23 2003-04-10 Microsoft Corporation Methods and systems for merging graphics for display on a computing device
US20030071818A1 (en) * 2001-03-23 2003-04-17 Microsoft Corporation Methods and systems for displaying animated graphics on a computing device
US6631349B1 (en) * 1997-11-27 2003-10-07 Hitachi, Ltd. Speech recognition method and system
US6671669B1 (en) * 2000-07-18 2003-12-30 Qualcomm Incorporated combined engine system and method for voice recognition
US20040047372A1 (en) * 1997-10-08 2004-03-11 Erik Boasson Techniques for communicating information using hermite-gaussian basis functions
US6754629B1 (en) * 2000-09-08 2004-06-22 Qualcomm Incorporated System and method for automatic voice recognition using mapping
US20040186717A1 (en) * 2003-03-17 2004-09-23 Rensselaer Polytechnic Institute System for reconstruction of symbols in a sequence
US20060192658A1 (en) * 2005-01-21 2006-08-31 Sanyo Electric Co., Ltd. Drive recorder and control method therefor
US7133827B1 (en) 2002-02-06 2006-11-07 Voice Signal Technologies, Inc. Training speech recognition word models from word samples synthesized by Monte Carlo techniques
US7319964B1 (en) * 1998-12-07 2008-01-15 At&T Corp. Method and apparatus for segmenting a multi-media program based upon audio events
US20090110207A1 (en) * 2006-05-01 2009-04-30 Nippon Telegraph And Telephone Company Method and Apparatus for Speech Dereverberation Based On Probabilistic Models Of Source And Room Acoustics
US20090238253A1 (en) * 1997-10-08 2009-09-24 Bandwidth Technology Corporation System and Method for Communicating Information Using Time-and-Frequency-Bounded Base Functions
US7630899B1 (en) 1998-06-15 2009-12-08 At&T Intellectual Property Ii, L.P. Concise dynamic grammars using N-best selection
US20110246196A1 (en) * 2010-03-30 2011-10-06 Aspen Networks, Inc. Integrated voice biometrics cloud security gateway
US8892446B2 (en) 2010-01-18 2014-11-18 Apple Inc. Service orchestration for intelligent automated assistant
US8977584B2 (en) 2010-01-25 2015-03-10 Newvaluexchange Global Ai Llp Apparatuses, methods and systems for a digital conversation management platform
US9262612B2 (en) 2011-03-21 2016-02-16 Apple Inc. Device access using voice authentication
US20160073215A1 (en) * 2013-05-16 2016-03-10 Koninklijke Philips N.V. An audio apparatus and method therefor
US9300784B2 (en) 2013-06-13 2016-03-29 Apple Inc. System and method for emergency calls initiated by voice command
US9330720B2 (en) 2008-01-03 2016-05-03 Apple Inc. Methods and apparatus for altering audio output signals
US9336774B1 (en) * 2012-04-20 2016-05-10 Google Inc. Pattern recognizing engine
US9338493B2 (en) 2014-06-30 2016-05-10 Apple Inc. Intelligent automated assistant for TV user interactions
US9368114B2 (en) 2013-03-14 2016-06-14 Apple Inc. Context-sensitive handling of interruptions
JP2016525813A (en) * 2014-01-02 2016-08-25 コーニンクレッカ フィリップス エヌ ヴェKoninklijke Philips N.V. Audio apparatus and method therefor
US9430463B2 (en) 2014-05-30 2016-08-30 Apple Inc. Exemplar-based natural language processing
US9483461B2 (en) 2012-03-06 2016-11-01 Apple Inc. Handling speech synthesis of content for multiple languages
US9495129B2 (en) 2012-06-29 2016-11-15 Apple Inc. Device, method, and user interface for voice-activated navigation and browsing of a document
US9502031B2 (en) 2014-05-27 2016-11-22 Apple Inc. Method for supporting dynamic grammars in WFST-based ASR
US9535906B2 (en) 2008-07-31 2017-01-03 Apple Inc. Mobile device having human language translation capability with positional feedback
US9576574B2 (en) 2012-09-10 2017-02-21 Apple Inc. Context-sensitive handling of interruptions by intelligent digital assistant
US9582608B2 (en) 2013-06-07 2017-02-28 Apple Inc. Unified ranking with entropy-weighted information for phrase-based semantic auto-completion
US20170092295A1 (en) * 2015-09-28 2017-03-30 GM Global Technology Operations LLC Streamlined navigational speech recognition
US9620105B2 (en) 2014-05-15 2017-04-11 Apple Inc. Analyzing audio input for efficient speech and music recognition
US9620104B2 (en) 2013-06-07 2017-04-11 Apple Inc. System and method for user-specified pronunciation of words for speech synthesis and recognition
US9626955B2 (en) 2008-04-05 2017-04-18 Apple Inc. Intelligent text-to-speech conversion
US9633004B2 (en) 2014-05-30 2017-04-25 Apple Inc. Better resolution when referencing to concepts
US9633660B2 (en) 2010-02-25 2017-04-25 Apple Inc. User profiling for voice input processing
US9633674B2 (en) 2013-06-07 2017-04-25 Apple Inc. System and method for detecting errors in interactions with a voice-based digital assistant
US9646609B2 (en) 2014-09-30 2017-05-09 Apple Inc. Caching apparatus for serving phonetic pronunciations
US9646614B2 (en) 2000-03-16 2017-05-09 Apple Inc. Fast, language-independent method for user authentication by voice
US9668121B2 (en) 2014-09-30 2017-05-30 Apple Inc. Social reminders
US9697820B2 (en) 2015-09-24 2017-07-04 Apple Inc. Unit-selection text-to-speech synthesis using concatenation-sensitive neural networks
US9697822B1 (en) 2013-03-15 2017-07-04 Apple Inc. System and method for updating an adaptive speech recognition model
US9711141B2 (en) 2014-12-09 2017-07-18 Apple Inc. Disambiguating heteronyms in speech synthesis
US9715875B2 (en) 2014-05-30 2017-07-25 Apple Inc. Reducing the need for manual start/end-pointing and trigger phrases
US9721566B2 (en) 2015-03-08 2017-08-01 Apple Inc. Competing devices responding to voice triggers
US9734193B2 (en) 2014-05-30 2017-08-15 Apple Inc. Determining domain salience ranking from ambiguous words in natural speech
US9760559B2 (en) 2014-05-30 2017-09-12 Apple Inc. Predictive text input
US9767807B2 (en) 2011-03-30 2017-09-19 Ack3 Bionetics Pte Limited Digital voice signature of transactions
US9785630B2 (en) 2014-05-30 2017-10-10 Apple Inc. Text prediction using combined word N-gram and unigram language models
US9798393B2 (en) 2011-08-29 2017-10-24 Apple Inc. Text correction processing
US9818400B2 (en) 2014-09-11 2017-11-14 Apple Inc. Method and apparatus for discovering trending terms in speech requests
US9842101B2 (en) 2014-05-30 2017-12-12 Apple Inc. Predictive conversion of language input
US9842105B2 (en) 2015-04-16 2017-12-12 Apple Inc. Parsimonious continuous-space phrase representations for natural language processing
US9858925B2 (en) 2009-06-05 2018-01-02 Apple Inc. Using context information to facilitate processing of commands in a virtual assistant
US9865280B2 (en) 2015-03-06 2018-01-09 Apple Inc. Structured dictation using intelligent automated assistants
US9886432B2 (en) 2014-09-30 2018-02-06 Apple Inc. Parsimonious handling of word inflection via categorical stem + suffix N-gram language models
US9886953B2 (en) 2015-03-08 2018-02-06 Apple Inc. Virtual assistant activation
US9899019B2 (en) 2015-03-18 2018-02-20 Apple Inc. Systems and methods for structured stem and suffix language models
US9922642B2 (en) 2013-03-15 2018-03-20 Apple Inc. Training an at least partial voice command system
US9934775B2 (en) 2016-05-26 2018-04-03 Apple Inc. Unit-selection text-to-speech synthesis based on predicted concatenation parameters
US9953088B2 (en) 2012-05-14 2018-04-24 Apple Inc. Crowd sourcing information to fulfill user requests
US9959870B2 (en) 2008-12-11 2018-05-01 Apple Inc. Speech recognition involving a mobile device
US9966065B2 (en) 2014-05-30 2018-05-08 Apple Inc. Multi-command single utterance input method
US9966068B2 (en) 2013-06-08 2018-05-08 Apple Inc. Interpreting and acting upon commands that involve sharing information with remote devices
US9971774B2 (en) 2012-09-19 2018-05-15 Apple Inc. Voice-based media searching
US9972304B2 (en) 2016-06-03 2018-05-15 Apple Inc. Privacy preserving distributed evaluation framework for embedded personalized systems
US10049668B2 (en) 2015-12-02 2018-08-14 Apple Inc. Applying neural network language models to weighted finite state transducers for automatic speech recognition
US10049663B2 (en) 2016-06-08 2018-08-14 Apple, Inc. Intelligent automated assistant for media exploration
US10057736B2 (en) 2011-06-03 2018-08-21 Apple Inc. Active transport based notifications
US10067938B2 (en) 2016-06-10 2018-09-04 Apple Inc. Multilingual word prediction
US10074360B2 (en) 2014-09-30 2018-09-11 Apple Inc. Providing an indication of the suitability of speech recognition
US10079014B2 (en) 2012-06-08 2018-09-18 Apple Inc. Name recognition system
US10078631B2 (en) 2014-05-30 2018-09-18 Apple Inc. Entropy-guided text prediction using combined word and character n-gram language models
US10083688B2 (en) 2015-05-27 2018-09-25 Apple Inc. Device voice control for selecting a displayed affordance
US10089072B2 (en) 2016-06-11 2018-10-02 Apple Inc. Intelligent device arbitration and control
US10101822B2 (en) 2015-06-05 2018-10-16 Apple Inc. Language input correction

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
GB8527913D0 (en) * 1985-11-12 1985-12-18 Pa Consulting Services Analysing transitions in finite state machines

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4348553A (en) * 1980-07-02 1982-09-07 International Business Machines Corporation Parallel pattern verifier with dynamic time warping
US4654875A (en) * 1983-05-23 1987-03-31 The Research Foundation Of State University Of New York System to achieve automatic recognition of linguistic strings

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4587670A (en) * 1982-10-15 1986-05-06 At&T Bell Laboratories Hidden Markov model speech recognition arrangement
US4741036A (en) * 1985-01-31 1988-04-26 International Business Machines Corporation Determination of phone weights for markov models in a speech recognition system

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4348553A (en) * 1980-07-02 1982-09-07 International Business Machines Corporation Parallel pattern verifier with dynamic time warping
US4654875A (en) * 1983-05-23 1987-03-31 The Research Foundation Of State University Of New York System to achieve automatic recognition of linguistic strings

Non-Patent Citations (10)

* Cited by examiner, † Cited by third party
Title
B. Juang et al., "Distortion Performance of Vector Quantization for LPC Voice Coding", IEEE Transactions on Acoustics, Speech and Signal Processing, vol. ASSP-30, No. 2, Apr. 1982, pp. 294-303.
B. Juang et al., Distortion Performance of Vector Quantization for LPC Voice Coding , IEEE Transactions on Acoustics, Speech and Signal Processing, vol. ASSP 30, No. 2, Apr. 1982, pp. 294 303. *
James K. Baker, "The Dragon System-An Overview", IEEE Transactions on Acoustics, Speech and Signal Processing, vol. ASSP-23, No. 1, Feb. 1975, pp. 24-29.
James K. Baker, The Dragon System An Overview , IEEE Transactions on Acoustics, Speech and Signal Processing, vol. ASSP 23, No. 1, Feb. 1975, pp. 24 29. *
L. R. Rabiner and J. G. Wilpon, "Considerations in Applying Clustering Techniques to Speaker-Independent Word Recognition", Journal of the Acoustical Society of America, 66(3), Sep. 1979, pp. 663-673.
L. R. Rabiner and J. G. Wilpon, Considerations in Applying Clustering Techniques to Speaker Independent Word Recognition , Journal of the Acoustical Society of America, 66(3), Sep. 1979, pp. 663 673. *
L. R. Rabiner et al., "On the Application of Vector Quantization and Hidden Markov Models to Speaker-Independent, Isolated Word Recognition", The Bell System Technical Journal, vol. 62, No. 4, Apr. 1983, pp. 1075-1105.
L. R. Rabiner et al., On the Application of Vector Quantization and Hidden Markov Models to Speaker Independent, Isolated Word Recognition , The Bell System Technical Journal, vol. 62, No. 4, Apr. 1983, pp. 1075 1105. *
Leonard E. Baum, "An Inequality and Associated Maximization Technique in Statistical Estimation for Probabilistic Functions of Markov Processes", Inequalities-III, 1972, pp. 1-8.
Leonard E. Baum, An Inequality and Associated Maximization Technique in Statistical Estimation for Probabilistic Functions of Markov Processes , Inequalities III, 1972, pp. 1 8. *

Cited By (190)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5377301A (en) * 1986-03-28 1994-12-27 At&T Corp. Technique for modifying reference vector quantized speech feature signals
US4852180A (en) * 1987-04-03 1989-07-25 American Telephone And Telegraph Company, At&T Bell Laboratories Speech recognition by acoustic/phonetic system and technique
US4918731A (en) * 1987-07-17 1990-04-17 Ricoh Company, Ltd. Speech recognition method and apparatus
US5072452A (en) * 1987-10-30 1991-12-10 International Business Machines Corporation Automatic determination of labels and Markov word models in a speech recognition system
US5129002A (en) * 1987-12-16 1992-07-07 Matsushita Electric Industrial Co., Ltd. Pattern recognition apparatus
US6047256A (en) * 1988-02-09 2000-04-04 Nec Corporation Device for generating a reference pattern with a continuous probability density function derived from feature code occurrence probability distribution
US5031217A (en) * 1988-09-30 1991-07-09 International Business Machines Corporation Speech recognition system using Markov models having independent label output sets
US5029212A (en) * 1988-10-03 1991-07-02 Nec Corporation Continuous speech recognition unit using forward probabilities
WO1990009644A1 (en) * 1989-02-07 1990-08-23 Smiths Industries Public Limited Company Monitoring
US5649057A (en) * 1989-05-17 1997-07-15 Lucent Technologies Inc. Speech recognition employing key word modeling and non-key word modeling
US5509104A (en) * 1989-05-17 1996-04-16 At&T Corp. Speech recognition employing key word modeling and non-key word modeling
US5075896A (en) * 1989-10-25 1991-12-24 Xerox Corporation Character and phoneme recognition based on probability clustering
US5307444A (en) * 1989-12-12 1994-04-26 Matsushita Electric Industrial Co., Ltd. Voice analyzing system using hidden Markov model and having plural neural network predictors
US5119425A (en) * 1990-01-02 1992-06-02 Raytheon Company Sound synthesizer
US5148489A (en) * 1990-02-28 1992-09-15 Sri International Method for spectral estimation to improve noise robustness for speech recognition
US5289562A (en) * 1990-09-13 1994-02-22 Mitsubishi Denki Kabushiki Kaisha Pattern representation model training apparatus
US5526465A (en) * 1990-10-03 1996-06-11 Ensigma Limited Methods and apparatus for verifying the originator of a sequence of operations
US5293451A (en) * 1990-10-23 1994-03-08 International Business Machines Corporation Method and apparatus for generating models of spoken words based on a small number of utterances
US5450523A (en) * 1990-11-15 1995-09-12 Matsushita Electric Industrial Co., Ltd. Training module for estimating mixture Gaussian densities for speech unit models in speech recognition systems
US5390278A (en) * 1991-10-08 1995-02-14 Bell Canada Phoneme based speech recognition
US5502790A (en) * 1991-12-24 1996-03-26 Oki Electric Industry Co., Ltd. Speech recognition method and system using triphones, diphones, and phonemes
US5544257A (en) * 1992-01-08 1996-08-06 International Business Machines Corporation Continuous parameter hidden Markov model approach to automatic handwriting recognition
US5636291A (en) * 1992-01-08 1997-06-03 International Business Machines Corporation Continuous parameter hidden Markov model approach to automatic handwriting recognition
DE4241688A1 (en) * 1992-03-21 1993-09-23 Atr Interpreting Telephony Res Generating sub-word model for speech recognition - successively dividing conditions in original model into temporal and contextual domains to form hidden Markow network using max. likelihood method
US5677988A (en) * 1992-03-21 1997-10-14 Atr Interpreting Telephony Research Laboratories Method of generating a subword model for speech recognition
US5233681A (en) * 1992-04-24 1993-08-03 International Business Machines Corporation Context-dependent speech recognizer using estimated next word context
US6434522B1 (en) * 1992-06-18 2002-08-13 Matsushita Electric Ind Co Ltd Combined quantized and continuous feature vector HMM approach to speech recognition
WO1994000836A1 (en) * 1992-06-29 1994-01-06 Kurzweil Applied Intelligence, Inc. Speech regognition system utilizing vocabulary model preselection
US5682464A (en) * 1992-06-29 1997-10-28 Kurzweil Applied Intelligence, Inc. Word model candidate preselection for speech recognition using precomputed matrix of thresholded distance values
US5386492A (en) * 1992-06-29 1995-01-31 Kurzweil Applied Intelligence, Inc. Speech recognition system utilizing vocabulary model preselection
US5333236A (en) * 1992-09-10 1994-07-26 International Business Machines Corporation Speech recognizer having a speech coder for an acoustic match based on context-dependent speech-transition acoustic models
US5787198A (en) * 1992-11-24 1998-07-28 Lucent Technologies Inc. Text recognition using two-dimensional stochastic models
US5452397A (en) * 1992-12-11 1995-09-19 Texas Instruments Incorporated Method and system for preventing entry of confusingly similar phases in a voice recognition system vocabulary list
US5596680A (en) * 1992-12-31 1997-01-21 Apple Computer, Inc. Method and apparatus for detecting speech activity using cepstrum vectors
US5692104A (en) * 1992-12-31 1997-11-25 Apple Computer, Inc. Method and apparatus for detecting end points of speech activity
US5535305A (en) * 1992-12-31 1996-07-09 Apple Computer, Inc. Sub-partitioned vector quantization of probability density functions
US5848388A (en) * 1993-03-25 1998-12-08 British Telecommunications Plc Speech recognition with sequence parsing, rejection and pause detection options
US5819222A (en) * 1993-03-31 1998-10-06 British Telecommunications Public Limited Company Task-constrained connected speech recognition of propagation of tokens only if valid propagation path is present
US6230128B1 (en) 1993-03-31 2001-05-08 British Telecommunications Public Limited Company Path link passing speech recognition with vocabulary node being capable of simultaneously processing plural path links
US5664058A (en) * 1993-05-12 1997-09-02 Nynex Science & Technology Method of training a speaker-dependent speech recognizer with automated supervision of training sufficiency
US5623609A (en) * 1993-06-14 1997-04-22 Hal Trust, L.L.C. Computer system and computer-implemented process for phonology-based automatic speech recognition
US5606644A (en) * 1993-07-22 1997-02-25 Lucent Technologies Inc. Minimum error rate training of combined string models
US5606643A (en) * 1994-04-12 1997-02-25 Xerox Corporation Real-time audio recording system for automatic speaker indexing
US5598507A (en) * 1994-04-12 1997-01-28 Xerox Corporation Method of speaker clustering for unknown speakers in conversational audio data
US5682501A (en) * 1994-06-22 1997-10-28 International Business Machines Corporation Speech synthesis system
US5825978A (en) * 1994-07-18 1998-10-20 Sri International Method and apparatus for speech recognition using optimized partial mixture tying of HMM state functions
US5625747A (en) * 1994-09-21 1997-04-29 Lucent Technologies Inc. Speaker verification, speech recognition and channel normalization through dynamic time/frequency warping
US5799277A (en) * 1994-10-25 1998-08-25 Victor Company Of Japan, Ltd. Acoustic model generating method for speech recognition
US5794198A (en) * 1994-10-28 1998-08-11 Nippon Telegraph And Telephone Corporation Pattern recognition method
US5832430A (en) * 1994-12-29 1998-11-03 Lucent Technologies, Inc. Devices and methods for speech recognition of vocabulary words with simultaneous detection and verification
US5991442A (en) * 1995-05-10 1999-11-23 Canon Kabushiki Kaisha Method and apparatus for pattern recognition utilizing gaussian distribution functions
US5719996A (en) * 1995-06-30 1998-02-17 Motorola, Inc. Speech recognition in selective call systems
US5806029A (en) * 1995-09-15 1998-09-08 At&T Corp Signal conditioned minimum error rate training for continuous speech recognition
US6049594A (en) * 1995-11-17 2000-04-11 At&T Corp Automatic vocabulary generation for telecommunications network-based voice-dialing
US7062435B2 (en) 1996-02-09 2006-06-13 Canon Kabushiki Kaisha Apparatus, method and computer readable memory medium for speech recognition using dynamic programming
US5960395A (en) * 1996-02-09 1999-09-28 Canon Kabushiki Kaisha Pattern matching method, apparatus and computer readable memory medium for speech recognition using dynamic programming
US20020032566A1 (en) * 1996-02-09 2002-03-14 Eli Tzirkel-Hancock Apparatus, method and computer readable memory medium for speech recogniton using dynamic programming
US5806030A (en) * 1996-05-06 1998-09-08 Matsushita Electric Ind Co Ltd Low complexity, high accuracy clustering method for speech recognizer
US5835890A (en) * 1996-08-02 1998-11-10 Nippon Telegraph And Telephone Corporation Method for speaker adaptation of speech models recognition scheme using the method and recording medium having the speech recognition method recorded thereon
US5865626A (en) * 1996-08-30 1999-02-02 Gte Internetworking Incorporated Multi-dialect speech recognition method and apparatus
US6137863A (en) * 1996-12-13 2000-10-24 At&T Corp. Statistical database correction of alphanumeric account numbers for speech recognition and touch-tone recognition
US6061654A (en) * 1996-12-16 2000-05-09 At&T Corp. System and method of recognizing letters and numbers by either speech or touch tone recognition utilizing constrained confusion matrices
US5848130A (en) * 1996-12-31 1998-12-08 At&T Corp System and method for enhanced intelligibility of voice messages
US5963902A (en) * 1997-07-30 1999-10-05 Nynex Science & Technology, Inc. Methods and apparatus for decreasing the size of generated models trained for automatic pattern recognition
US5950158A (en) * 1997-07-30 1999-09-07 Nynex Science And Technology, Inc. Methods and apparatus for decreasing the size of pattern recognition models by pruning low-scoring models from generated sets of models
US6154579A (en) * 1997-08-11 2000-11-28 At&T Corp. Confusion matrix based method and system for correcting misrecognized words appearing in documents generated by an optical character recognition technique
US6219453B1 (en) 1997-08-11 2001-04-17 At&T Corp. Method and apparatus for performing an automatic correction of misrecognized words produced by an optical character recognition technique by using a Hidden Markov Model based algorithm
US6246980B1 (en) * 1997-09-29 2001-06-12 Matra Nortel Communications Method of speech recognition
US7894326B2 (en) 1997-10-08 2011-02-22 Bandwidth Technology Corp. System and method for communicating information using time-and-frequency-bounded base functions
US20090238253A1 (en) * 1997-10-08 2009-09-24 Bandwidth Technology Corporation System and Method for Communicating Information Using Time-and-Frequency-Bounded Base Functions
US20040047372A1 (en) * 1997-10-08 2004-03-11 Erik Boasson Techniques for communicating information using hermite-gaussian basis functions
US6898207B2 (en) * 1997-10-08 2005-05-24 Bandwidth Technology Corp. Techniques for communicating information using Hermite-Gaussian basis functions
US6141661A (en) * 1997-10-17 2000-10-31 At&T Corp Method and apparatus for performing a grammar-pruning operation
US6205428B1 (en) 1997-11-20 2001-03-20 At&T Corp. Confusion set-base method and apparatus for pruning a predetermined arrangement of indexed identifiers
US6208965B1 (en) 1997-11-20 2001-03-27 At&T Corp. Method and apparatus for performing a name acquisition based on speech recognition
US6122612A (en) * 1997-11-20 2000-09-19 At&T Corp Check-sum based method and apparatus for performing speech recognition
US6631349B1 (en) * 1997-11-27 2003-10-07 Hitachi, Ltd. Speech recognition method and system
US6205261B1 (en) 1998-02-05 2001-03-20 At&T Corp. Confusion set based method and system for correcting misrecognized words appearing in documents generated by an optical character recognition technique
US6400805B1 (en) 1998-06-15 2002-06-04 At&T Corp. Statistical database correction of alphanumeric identifiers for speech recognition and touch-tone recognition
US9286887B2 (en) 1998-06-15 2016-03-15 At&T Intellectual Property Ii, L.P. Concise dynamic grammars using N-best selection
US7937260B1 (en) 1998-06-15 2011-05-03 At&T Intellectual Property Ii, L.P. Concise dynamic grammars using N-best selection
US20110202343A1 (en) * 1998-06-15 2011-08-18 At&T Intellectual Property I, L.P. Concise dynamic grammars using n-best selection
US7630899B1 (en) 1998-06-15 2009-12-08 At&T Intellectual Property Ii, L.P. Concise dynamic grammars using N-best selection
US8682665B2 (en) 1998-06-15 2014-03-25 At&T Intellectual Property Ii, L.P. Concise dynamic grammars using N-best selection
US6269334B1 (en) * 1998-06-25 2001-07-31 International Business Machines Corporation Nongaussian density estimation for the classification of acoustic feature vectors in speech recognition
US6157731A (en) * 1998-07-01 2000-12-05 Lucent Technologies Inc. Signature verification method using hidden markov models
US8560319B1 (en) 1998-12-07 2013-10-15 At&T Intellectual Property Ii, L.P. Method and apparatus for segmenting a multimedia program based upon audio events
US7319964B1 (en) * 1998-12-07 2008-01-15 At&T Corp. Method and apparatus for segmenting a multi-media program based upon audio events
US9646614B2 (en) 2000-03-16 2017-05-09 Apple Inc. Fast, language-independent method for user authentication by voice
US6671669B1 (en) * 2000-07-18 2003-12-30 Qualcomm Incorporated combined engine system and method for voice recognition
US6754629B1 (en) * 2000-09-08 2004-06-22 Qualcomm Incorporated System and method for automatic voice recognition using mapping
US20030067467A1 (en) * 2001-03-23 2003-04-10 Microsoft Corporation Methods and systems for merging graphics for display on a computing device
US7315308B2 (en) 2001-03-23 2008-01-01 Microsoft Corporation Methods and system for merging graphics for display on a computing device
US7239324B2 (en) 2001-03-23 2007-07-03 Microsoft Corporation Methods and systems for merging graphics for display on a computing device
US7439981B2 (en) 2001-03-23 2008-10-21 Microsoft Corporation Methods and systems for displaying animated graphics on a computing device
US20040212621A1 (en) * 2001-03-23 2004-10-28 Microsoft Corporation Methods and systems for merging graphics for display on a computing device
US20040217960A1 (en) * 2001-03-23 2004-11-04 Microsoft Corporation Methods and systems for merging graphics for display on a computing device
US20030071818A1 (en) * 2001-03-23 2003-04-17 Microsoft Corporation Methods and systems for displaying animated graphics on a computing device
US7315307B2 (en) 2001-03-23 2008-01-01 Microsoft Corporation Methods and systems for merging graphics for display on a computing device
US20050083339A1 (en) * 2001-03-23 2005-04-21 Microsoft Corporation Methods and systems for displaying animated graphics on a computing device
US7133827B1 (en) 2002-02-06 2006-11-07 Voice Signal Technologies, Inc. Training speech recognition word models from word samples synthesized by Monte Carlo techniques
CN1830188B (en) 2002-12-20 2011-04-06 带宽科技有限公司 System and method for communicating digital information using time-and-frequency-bounded base functions
US20040186717A1 (en) * 2003-03-17 2004-09-23 Rensselaer Polytechnic Institute System for reconstruction of symbols in a sequence
US7024360B2 (en) * 2003-03-17 2006-04-04 Rensselaer Polytechnic Institute System for reconstruction of symbols in a sequence
US20060192658A1 (en) * 2005-01-21 2006-08-31 Sanyo Electric Co., Ltd. Drive recorder and control method therefor
US8290170B2 (en) * 2006-05-01 2012-10-16 Nippon Telegraph And Telephone Corporation Method and apparatus for speech dereverberation based on probabilistic models of source and room acoustics
US20090110207A1 (en) * 2006-05-01 2009-04-30 Nippon Telegraph And Telephone Company Method and Apparatus for Speech Dereverberation Based On Probabilistic Models Of Source And Room Acoustics
US8930191B2 (en) 2006-09-08 2015-01-06 Apple Inc. Paraphrasing of user requests and results by automated digital assistant
US8942986B2 (en) 2006-09-08 2015-01-27 Apple Inc. Determining user intent based on ontologies of domains
US9117447B2 (en) 2006-09-08 2015-08-25 Apple Inc. Using event alert text as input to an automated assistant
US9330720B2 (en) 2008-01-03 2016-05-03 Apple Inc. Methods and apparatus for altering audio output signals
US9626955B2 (en) 2008-04-05 2017-04-18 Apple Inc. Intelligent text-to-speech conversion
US9865248B2 (en) 2008-04-05 2018-01-09 Apple Inc. Intelligent text-to-speech conversion
US10108612B2 (en) 2008-07-31 2018-10-23 Apple Inc. Mobile device having human language translation capability with positional feedback
US9535906B2 (en) 2008-07-31 2017-01-03 Apple Inc. Mobile device having human language translation capability with positional feedback
US9959870B2 (en) 2008-12-11 2018-05-01 Apple Inc. Speech recognition involving a mobile device
US9858925B2 (en) 2009-06-05 2018-01-02 Apple Inc. Using context information to facilitate processing of commands in a virtual assistant
US9318108B2 (en) 2010-01-18 2016-04-19 Apple Inc. Intelligent automated assistant
US8892446B2 (en) 2010-01-18 2014-11-18 Apple Inc. Service orchestration for intelligent automated assistant
US8903716B2 (en) 2010-01-18 2014-12-02 Apple Inc. Personalized vocabulary for digital assistant
US9548050B2 (en) 2010-01-18 2017-01-17 Apple Inc. Intelligent automated assistant
US8977584B2 (en) 2010-01-25 2015-03-10 Newvaluexchange Global Ai Llp Apparatuses, methods and systems for a digital conversation management platform
US9424862B2 (en) 2010-01-25 2016-08-23 Newvaluexchange Ltd Apparatuses, methods and systems for a digital conversation management platform
US9424861B2 (en) 2010-01-25 2016-08-23 Newvaluexchange Ltd Apparatuses, methods and systems for a digital conversation management platform
US9431028B2 (en) 2010-01-25 2016-08-30 Newvaluexchange Ltd Apparatuses, methods and systems for a digital conversation management platform
US9633660B2 (en) 2010-02-25 2017-04-25 Apple Inc. User profiling for voice input processing
US10049675B2 (en) 2010-02-25 2018-08-14 Apple Inc. User profiling for voice input processing
US20110246196A1 (en) * 2010-03-30 2011-10-06 Aspen Networks, Inc. Integrated voice biometrics cloud security gateway
US9412381B2 (en) * 2010-03-30 2016-08-09 Ack3 Bionetics Private Ltd. Integrated voice biometrics cloud security gateway
US9262612B2 (en) 2011-03-21 2016-02-16 Apple Inc. Device access using voice authentication
US10102359B2 (en) 2011-03-21 2018-10-16 Apple Inc. Device access using voice authentication
US9767807B2 (en) 2011-03-30 2017-09-19 Ack3 Bionetics Pte Limited Digital voice signature of transactions
US10057736B2 (en) 2011-06-03 2018-08-21 Apple Inc. Active transport based notifications
US9798393B2 (en) 2011-08-29 2017-10-24 Apple Inc. Text correction processing
US9483461B2 (en) 2012-03-06 2016-11-01 Apple Inc. Handling speech synthesis of content for multiple languages
US9336774B1 (en) * 2012-04-20 2016-05-10 Google Inc. Pattern recognizing engine
US9953088B2 (en) 2012-05-14 2018-04-24 Apple Inc. Crowd sourcing information to fulfill user requests
US10079014B2 (en) 2012-06-08 2018-09-18 Apple Inc. Name recognition system
US9495129B2 (en) 2012-06-29 2016-11-15 Apple Inc. Device, method, and user interface for voice-activated navigation and browsing of a document
US9576574B2 (en) 2012-09-10 2017-02-21 Apple Inc. Context-sensitive handling of interruptions by intelligent digital assistant
US9971774B2 (en) 2012-09-19 2018-05-15 Apple Inc. Voice-based media searching
US9368114B2 (en) 2013-03-14 2016-06-14 Apple Inc. Context-sensitive handling of interruptions
US9922642B2 (en) 2013-03-15 2018-03-20 Apple Inc. Training an at least partial voice command system
US9697822B1 (en) 2013-03-15 2017-07-04 Apple Inc. System and method for updating an adaptive speech recognition model
US20160073215A1 (en) * 2013-05-16 2016-03-10 Koninklijke Philips N.V. An audio apparatus and method therefor
US9860669B2 (en) * 2013-05-16 2018-01-02 Koninklijke Philips N.V. Audio apparatus and method therefor
US9582608B2 (en) 2013-06-07 2017-02-28 Apple Inc. Unified ranking with entropy-weighted information for phrase-based semantic auto-completion
US9633674B2 (en) 2013-06-07 2017-04-25 Apple Inc. System and method for detecting errors in interactions with a voice-based digital assistant
US9966060B2 (en) 2013-06-07 2018-05-08 Apple Inc. System and method for user-specified pronunciation of words for speech synthesis and recognition
US9620104B2 (en) 2013-06-07 2017-04-11 Apple Inc. System and method for user-specified pronunciation of words for speech synthesis and recognition
US9966068B2 (en) 2013-06-08 2018-05-08 Apple Inc. Interpreting and acting upon commands that involve sharing information with remote devices
US9300784B2 (en) 2013-06-13 2016-03-29 Apple Inc. System and method for emergency calls initiated by voice command
JP2016525813A (en) * 2014-01-02 2016-08-25 コーニンクレッカ フィリップス エヌ ヴェKoninklijke Philips N.V. Audio apparatus and method therefor
US9620105B2 (en) 2014-05-15 2017-04-11 Apple Inc. Analyzing audio input for efficient speech and music recognition
US9502031B2 (en) 2014-05-27 2016-11-22 Apple Inc. Method for supporting dynamic grammars in WFST-based ASR
US10083690B2 (en) 2014-05-30 2018-09-25 Apple Inc. Better resolution when referencing to concepts
US9842101B2 (en) 2014-05-30 2017-12-12 Apple Inc. Predictive conversion of language input
US9760559B2 (en) 2014-05-30 2017-09-12 Apple Inc. Predictive text input
US9715875B2 (en) 2014-05-30 2017-07-25 Apple Inc. Reducing the need for manual start/end-pointing and trigger phrases
US9734193B2 (en) 2014-05-30 2017-08-15 Apple Inc. Determining domain salience ranking from ambiguous words in natural speech
US10078631B2 (en) 2014-05-30 2018-09-18 Apple Inc. Entropy-guided text prediction using combined word and character n-gram language models
US9430463B2 (en) 2014-05-30 2016-08-30 Apple Inc. Exemplar-based natural language processing
US9785630B2 (en) 2014-05-30 2017-10-10 Apple Inc. Text prediction using combined word N-gram and unigram language models
US9633004B2 (en) 2014-05-30 2017-04-25 Apple Inc. Better resolution when referencing to concepts
US9966065B2 (en) 2014-05-30 2018-05-08 Apple Inc. Multi-command single utterance input method
US9338493B2 (en) 2014-06-30 2016-05-10 Apple Inc. Intelligent automated assistant for TV user interactions
US9668024B2 (en) 2014-06-30 2017-05-30 Apple Inc. Intelligent automated assistant for TV user interactions
US9818400B2 (en) 2014-09-11 2017-11-14 Apple Inc. Method and apparatus for discovering trending terms in speech requests
US9646609B2 (en) 2014-09-30 2017-05-09 Apple Inc. Caching apparatus for serving phonetic pronunciations
US9886432B2 (en) 2014-09-30 2018-02-06 Apple Inc. Parsimonious handling of word inflection via categorical stem + suffix N-gram language models
US9668121B2 (en) 2014-09-30 2017-05-30 Apple Inc. Social reminders
US9986419B2 (en) 2014-09-30 2018-05-29 Apple Inc. Social reminders
US10074360B2 (en) 2014-09-30 2018-09-11 Apple Inc. Providing an indication of the suitability of speech recognition
US9711141B2 (en) 2014-12-09 2017-07-18 Apple Inc. Disambiguating heteronyms in speech synthesis
US9865280B2 (en) 2015-03-06 2018-01-09 Apple Inc. Structured dictation using intelligent automated assistants
US9721566B2 (en) 2015-03-08 2017-08-01 Apple Inc. Competing devices responding to voice triggers
US9886953B2 (en) 2015-03-08 2018-02-06 Apple Inc. Virtual assistant activation
US9899019B2 (en) 2015-03-18 2018-02-20 Apple Inc. Systems and methods for structured stem and suffix language models
US9842105B2 (en) 2015-04-16 2017-12-12 Apple Inc. Parsimonious continuous-space phrase representations for natural language processing
US10083688B2 (en) 2015-05-27 2018-09-25 Apple Inc. Device voice control for selecting a displayed affordance
US10101822B2 (en) 2015-06-05 2018-10-16 Apple Inc. Language input correction
US9697820B2 (en) 2015-09-24 2017-07-04 Apple Inc. Unit-selection text-to-speech synthesis using concatenation-sensitive neural networks
US20170092295A1 (en) * 2015-09-28 2017-03-30 GM Global Technology Operations LLC Streamlined navigational speech recognition
US10008201B2 (en) * 2015-09-28 2018-06-26 GM Global Technology Operations LLC Streamlined navigational speech recognition
US10049668B2 (en) 2015-12-02 2018-08-14 Apple Inc. Applying neural network language models to weighted finite state transducers for automatic speech recognition
US9934775B2 (en) 2016-05-26 2018-04-03 Apple Inc. Unit-selection text-to-speech synthesis based on predicted concatenation parameters
US9972304B2 (en) 2016-06-03 2018-05-15 Apple Inc. Privacy preserving distributed evaluation framework for embedded personalized systems
US10049663B2 (en) 2016-06-08 2018-08-14 Apple, Inc. Intelligent automated assistant for media exploration
US10067938B2 (en) 2016-06-10 2018-09-04 Apple Inc. Multilingual word prediction
US10089072B2 (en) 2016-06-11 2018-10-02 Apple Inc. Intelligent device arbitration and control

Also Published As

Publication number Publication date Type
FR2579357B1 (en) 1990-01-12 grant
JPS61262799A (en) 1986-11-20 application
JPH0555040B2 (en) 1993-08-16 grant
FR2579357A1 (en) 1986-09-26 application

Similar Documents

Publication Publication Date Title
Mak et al. Phone clustering using the Bhattacharyya distance
US4837831A (en) Method for creating and using multiple-word sound models in speech recognition
US6138095A (en) Speech recognition
Juang et al. Hidden Markov models for speech recognition
US5046099A (en) Adaptation of acoustic prototype vectors in a speech recognition system
US5675706A (en) Vocabulary independent discriminative utterance verification for non-keyword rejection in subword based speech recognition
Picone Signal modeling techniques in speech recognition
US6078884A (en) Pattern recognition
US5873061A (en) Method for constructing a model of a new word for addition to a word model database of a speech recognition system
US4624011A (en) Speech recognition system
US5621809A (en) Computer program product for automatic recognition of a consistent message using multiple complimentary sources of information
US6418412B1 (en) Quantization using frequency and mean compensated frequency input data for robust speech recognition
US5839105A (en) Speaker-independent model generation apparatus and speech recognition apparatus each equipped with means for splitting state having maximum increase in likelihood
US5664059A (en) Self-learning speaker adaptation based on spectral variation source decomposition
US5742928A (en) Apparatus and method for speech recognition in the presence of unnatural speech effects
US5953701A (en) Speech recognition models combining gender-dependent and gender-independent phone states and using phonetic-context-dependence
US4348553A (en) Parallel pattern verifier with dynamic time warping
US5812975A (en) State transition model design method and voice recognition method and apparatus using same
US5222146A (en) Speech recognition apparatus having a speech coder outputting acoustic prototype ranks
Zissman Automatic language identification using Gaussian mixture and hidden Markov models
US6064958A (en) Pattern recognition scheme using probabilistic models based on mixtures distribution of discrete distribution
US5625748A (en) Topic discriminator using posterior probability or confidence scores
EP0570660A1 (en) Speech recognition system for natural language translation
US5745873A (en) Speech recognition using final decision based on tentative decisions
US6985858B2 (en) Method and apparatus for removing noise from feature vectors

Legal Events

Date Code Title Description
AS Assignment

Owner name: BELL TELEPHONE LABORATORIES, INCORPORATED 600 MOUN

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST.;ASSIGNORS:JUANG, BIING-HWANG;LEVINSON, STEPHEN E.;RABINER, LAWRENCE R.;AND OTHERS;REEL/FRAME:004422/0271;SIGNING DATES FROM 19850319 TO 19850321

FPAY Fee payment

Year of fee payment: 4

FPAY Fee payment

Year of fee payment: 8

FPAY Fee payment

Year of fee payment: 12